I want to draw a meta plot with Mantel-Haenszel analysis (meta.MH) in the "rmeta" package. Is it possible to change the confidence interval? The default is 95%, but what if I want, say 99% or 90% confidence interval? I can't seem to find how to do this in the manual. Thanks. -- ----------------------------------------------------------------------------------- Ko-Kang Wang Undergraduate Student Computer Science/Statistics Double Major University of Auckland Auckland 1005 New Zealand ----------------------------------------------------------------------------------- -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html Send "info", "help", or "[un]subscribe" (in the "body", not the subject !) To: r-help-request at stat.math.ethz.ch _._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._
rmeta Package
3 messages · Peter Dalgaard, Ko-Kang Kevin Wang
Ko-Kang Wang <Ko-Kang at xtra.co.nz> writes:
I want to draw a meta plot with Mantel-Haenszel analysis (meta.MH) in the "rmeta" package. Is it possible to change the confidence interval? The default is 95%, but what if I want, say 99% or 90% confidence interval? I can't seem to find how to do this in the manual. Thanks.
There are multiple hardcoded "1.96"s in the code for metaplot() and summary.meta.MH(). You'd have to replace those with -qnorm((1-conf.level)/2) (== 2.576 and 1.645 for 99% resp. 90%) either manually changing the value or - better - by adding a parameter to the routines (and contributing your fixes back to the maintainer).
O__ ---- Peter Dalgaard Blegdamsvej 3 c/ /'_ --- Dept. of Biostatistics 2200 Cph. N (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918 ~~~~~~~~~~ - (p.dalgaard at biostat.ku.dk) FAX: (+45) 35327907 -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html Send "info", "help", or "[un]subscribe" (in the "body", not the subject !) To: r-help-request at stat.math.ethz.ch _._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._
To Thomas, I have made some attemp to add the ability to change the level of confidence interval into your rmeta package. Currently I've successfully (although I've just tested on 1 data set which worked) changed meta.MH, I will try to add the parameter into meta.DSL. My question is, would you like me to send you the rmeta.R file after I've added the new parameter (currently the changes have been saved under MyMeta.R)? Or I shall just keep the file myself for private use? I think it will be kind of great if I send it to you after I finish and you may want to upgrade the package, since it will be much more convinient to be able to specify the confidence interval without having to go through the actual code behind the function. Cheers, Ko-Kang
Peter Dalgaard BSA wrote:
Ko-Kang Wang <Ko-Kang at xtra.co.nz> writes:
I want to draw a meta plot with Mantel-Haenszel analysis (meta.MH) in the "rmeta" package. Is it possible to change the confidence interval? The default is 95%, but what if I want, say 99% or 90% confidence interval? I can't seem to find how to do this in the manual. Thanks.
There are multiple hardcoded "1.96"s in the code for metaplot() and summary.meta.MH(). You'd have to replace those with -qnorm((1-conf.level)/2) (== 2.576 and 1.645 for 99% resp. 90%) either manually changing the value or - better - by adding a parameter to the routines (and contributing your fixes back to the maintainer). -- O__ ---- Peter Dalgaard Blegdamsvej 3 c/ /'_ --- Dept. of Biostatistics 2200 Cph. N (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918 ~~~~~~~~~~ - (p.dalgaard at biostat.ku.dk) FAX: (+45) 35327907
-- ----------------------------------------------------------------------------------- Ko-Kang Wang Undergraduate Student Computer Science/Statistics Double Major University of Auckland Auckland 1005 New Zealand ----------------------------------------------------------------------------------- -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html Send "info", "help", or "[un]subscribe" (in the "body", not the subject !) To: r-help-request at stat.math.ethz.ch _._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._